Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to background information and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    context for understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.50
    IBOutlet
    -0.46
    İstinadlar
    -0.46
    initComponents
    -0.45
    ۜ
    -0.45
     cjs
    -0.45
     fand
    -0.44
    Gef
    -0.44
    Jsp
    -0.44
    ="@+
    -0.44
    POSITIVE LOGITS
     Hintergrund
    0.63
     contexte
    0.58
     background
    0.55
     BACKGROUND
    0.54
    Background
    0.54
     bakgrund
    0.52
    background
    0.51
     achtergrond
    0.50
     forklar
    0.47
     Background
    0.47
    Act Density 0.155%

    No Known Activations